Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130983
    Prev
    Next
    INDEX
    Explanations

    ord

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interact
    -0.08
    becue
    -0.08
    beda
    -0.08
    CED
    -0.08
    ced
    -0.07
    Sdk
    -0.07
    zag
    -0.07
    -sdk
    -0.07
    cing
    -0.07
    Overlap
    -0.07
    POSITIVE LOGITS
    ord
    0.16
    ORD
    0.15
    ords
    0.15
    орд
    0.14
    ોર્ડ
    0.13
    ording
    0.12
     ORD
    0.12
    র্ড
    0.12
    ordre
    0.12
    ॉर्ड
    0.12
    Activations Density 0.001%

    No Known Activations